I built a Bitbucket CLI — and it convinced me CLIs beat MCP servers for AI agents

Hugo Hebert — Fri, 17 Apr 2026 00:49:20 +0000

GitHub has gh. GitLab has glab. Bitbucket Cloud has..??

It's called bb.

The obvious surface, done properly:

bb pr list                 # open PRs, most recent first
bb pr view 42              # details, reviewers, status — no browser
bb pr diff 42              # raw diff, pipeable into less / delta / anything
bb pr merge 42             # merge, squash, or fast-forward
bb pipeline wait           # blocks until the current build finishes

When I started, the plan was: CLI first, then wrap it in an MCP server so Claude Code and Cursor could call it. MCP is the fashionable way to give an agent tools right now. Every devtool company is shipping one.

Then I tried the lazy version first — just let the agent shell out to bb directly — and never went back.

Here's why I think CLIs are actually the better interface for AI agents, and MCP is solving a problem most tools don't have.

1. Tool schemas burn context on every turn. An MCP server advertises its tools as JSON schemas that get injected into the model's context every message. Twelve tools, twelve schemas, every turn. A CLI adverti
ses itself once, through --help, and the agent remembers the shape. You pay the tokens once, not forever.

2. Shell is the universal tool protocol. Every agent framework — Claude Code, Cursor, Aider, Codex, the next one — already knows how to run bash. bb pr view 42 works the day you install it, in every tool, with zero integration code. MCP needs a client that speaks MCP. That's a non-trivial coupling for something that was always going to be a subprocess under the hood.

3. Composition is free. This is the big one:

bb pr list --output-style ai | grep OPEN | head -5
bb pipeline latest --output-style ai | jq -r .status
bb pr diff 42 | wc -l

An agent can pipe, filter, count, and chain — all using primitives it already knows. An MCP tool is a sealed function call. You can't grep an MCP response. You can't pipe it into jq. Every slice and dice has to be a new tool or a new argument.

4. You can debug it. When the agent does something weird, I run the exact command it ran and see the exact output it saw. With MCP, the agent sees a structured payload the server built, and I'm reading logs trying to reconstruct what happened.

5. Distribution is solved. npm install -g and you're done. No config file, no server process, no "restart your editor so the tool picks up." The agent inherits the tool the moment the shell does.

The one thing CLIs owe to agents

There is one place existing CLIs fall short for agents, and it's fixable: default output. Box-drawing characters and ANSI colours are hostile to a model. So every bb command has a third mode next to the defau
lt and --json:

bb pr list --output-style ai

42  OPEN    Fix auth token refresh       hugo
41  MERGED  Add env variable endpoint    sara

Tab-separated. No colour. No borders. Set it as the default with bb option --output-style ai and an agent reads the output in one pass.

That's it. That's the whole adaptation. No server, no schema, no protocol — just an output mode. You get 95% of what an MCP server gives you, with none of the integration tax.

Try it

npm install -g @hugo-hebert/bbucket-cli
bb auth
bb pr list

Repo: https://github.com/Hugo-Hbrt/bbucket-cli
Docs: https://hugo-hbrt.github.io/bbucket-cli/

I Built a VS Code Extension to Visualize JSON as Tree Diagrams

Hugo Hebert — Thu, 25 Dec 2025 01:05:08 +0000

The Problem

We've all been there. You're debugging an API response, staring at a 500-line JSON file, hunting for that one nested field buried three levels deep. You're mentally matching brackets, losing your place, scrolling up and down.

{
  "users": [
    {
      "id": 1,
      "profile": {
        "settings": {
          "notifications": {
            "email": {
              "frequency": "weekly"  // <- Where is this thing?!
            }
          }
        }
      }
    }
  ]
}

I got tired of this. So I built JSON Diagram Viewer.

The Solution

One click transforms your JSON into an interactive, collapsible tree diagram right inside VS Code. No more bracket matching. No more getting lost.

Key Features

Live Sync - Edit your JSON, watch the diagram update in real-time. No refresh needed.

Color-Coded Cards - Objects, arrays, and primitives each have distinct colors so you can scan the structure at a glance.

Collapsible Nodes - Click to expand/collapse any section. Focus on what matters.

Copy Path & Values - Right-click any node to copy its JSON path (users[0].profile.settings) or value.

How to Use It

Install from the VS Code Marketplace
Open any .json file
Right-click → View as Diagram

That's it. The diagram opens side-by-side with your editor.

Use Cases

API Development - Visualize responses from REST/GraphQL endpoints
Config Files - Navigate package.json, tsconfig.json, or any complex config
Data Analysis - Explore JSON datasets before processing
Debugging - Understand nested state objects in React/Vue devtools exports

Built With

TypeScript
VS Code Webview API
React for the rendering, bundled with Vite.

Try It Out

👉 VS Code Marketplace

👉 GitHub (MIT licensed, contributions welcome!)

What JSON visualization pain points do you have? Let me know in the comments!

DEV Community: Hugo Hebert